On 10/31/25 03:49, Mohamed Ahmed wrote:> From: Mary Guillemard <mary at mary.zone>
>
> Now that everything in UVMM knows about the variable page shift, we can
> select larger values.
>
> The proposed approach relies on nouveau_bo::page unless if it would cause
> alignment issues (in which case we fall back to searching for an
> appropriate shift)
>
> Signed-off-by: Mary Guillemard <mary at mary.zone>
> Co-developed-by: Mohamed Ahmed <mohamedahmedegypt2001 at gmail.com>
> Signed-off-by: Mohamed Ahmed <mohamedahmedegypt2001 at gmail.com>
> ---
> drivers/gpu/drm/nouveau/nouveau_uvmm.c | 60 +++++++++++++++++++++++++-
> 1 file changed, 58 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
> index 2cd0835b05e8..ab8933b88337 100644
> --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
> +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
> @@ -454,6 +454,62 @@ op_unmap_prepare_unwind(struct drm_gpuva *va)
> drm_gpuva_insert(va->vm, va);
> }
>
> +static bool
> +op_map_aligned_to_page_shift(const struct drm_gpuva_op_map *op, u8
page_shift)
> +{
> + u64 non_page_bits = (1ULL << page_shift) - 1;
> +
> + return (op->va.addr & non_page_bits) == 0 &&
> + (op->va.range & non_page_bits) == 0 &&
> + (op->gem.offset & non_page_bits) == 0;
> +}
> +
> +static u8
> +select_page_shift(struct nouveau_uvmm *uvmm, struct drm_gpuva_op_map *op)
> +{
> + struct nouveau_bo *nvbo = nouveau_gem_object(op->gem.obj);
> +
> + /* nouveau_bo_fixup_align() guarantees that the page size will be aligned
> + * for most cases, but it can't handle cases where userspace
allocates with
> + * a size and then binds with a smaller granularity. So in order to avoid
> + * breaking old userspace, we need to ensure that the VA is actually
> + * aligned before using it, and if it isn't, then we downgrade to the
first
> + * granularity that will fit, which is optimal from a correctness and
> + * performance perspective.
> + */
> + if (op_map_aligned_to_page_shift(op, nvbo->page))
> + return nvbo->page;
> +
> + struct nouveau_mem *mem = nouveau_mem(nvbo->bo.resource);
> + struct nvif_vmm *vmm = &uvmm->vmm.vmm;
> + int i;
> +
> + /* If the given granularity doesn't fit, let's find one that will
fit. */
> + for (i = 0; i < vmm->page_nr; i++) {
> + /* Ignore anything that is bigger or identical to the BO preference. */
> + if (vmm->page[i].shift >= nvbo->page)
> + continue;
> +
> + /* Skip incompatible domains. */
> + if ((mem->mem.type & NVIF_MEM_VRAM) &&
!vmm->page[i].vram)
> + continue;
> + if ((mem->mem.type & NVIF_MEM_HOST) &&
> + (!vmm->page[i].host || vmm->page[i].shift > PAGE_SHIFT))
> + continue;
This logic doesn't seem correct. I'm not sure why there's a need to
limit the page size on the host memory type, but assuming there is due
to nouveau architecture or HW limitations I'm not aware of, it should be
applied universally, not just when falling back due to misaligned
addresses. You can get lucky and have aligned addresses regardless of
the target page size. Hence, this check would need to precede the above
early-out for the case where op_map_aligned_to_page_shift() succeeds.
Thanks,
-James
> + /* If it fits, return the proposed shift. */
> + if (op_map_aligned_to_page_shift(op, vmm->page[i].shift))
> + return vmm->page[i].shift;
> + }
> +
> + /* If we get here then nothing can reconcile the requirements. This
should never
> + * happen.
> + */
> + WARN_ON(1);
> +
> + return PAGE_SHIFT;
> +}
> +
> static void
> nouveau_uvmm_sm_prepare_unwind(struct nouveau_uvmm *uvmm,
> struct nouveau_uvma_prealloc *new,
> @@ -506,7 +562,7 @@ nouveau_uvmm_sm_prepare_unwind(struct nouveau_uvmm
*uvmm,
> if (vmm_get_range)
> nouveau_uvmm_vmm_put(uvmm, vmm_get_start,
> vmm_get_range,
> - PAGE_SHIFT);
> + select_page_shift(uvmm, &op->map));
> break;
> }
> case DRM_GPUVA_OP_REMAP: {
> @@ -599,7 +655,7 @@ op_map_prepare(struct nouveau_uvmm *uvmm,
>
> uvma->region = args->region;
> uvma->kind = args->kind;
> - uvma->page_shift = PAGE_SHIFT;
> + uvma->page_shift = select_page_shift(uvmm, op);
>
> drm_gpuva_map(&uvmm->base, &uvma->va, op);
>